@_akhaliq - AI Dynamics - Page 101 of 140

Cross-lingual NLP Testing Using Typological Features

By

–

12 July 2023 3h16

Empowering Cross-lingual Behavioral Testing of NLP Models with Typological Features paper page: https://
huggingface.co/papers/2307.05
454
… A challenge towards developing NLP systems for the world's languages is understanding how they generalize to typological differences relevant for real-world

→ View original post on X — @_akhaliq

12 July 2023

Cognitive Synergy in LLMs: Multi-Persona Self-Collaboration Agent

By

@_akhaliq

–

12 July 2023 3h11

Unleashing Cognitive Synergy in Large Language Models: A Task-Solving Agent through Multi-Persona Self-Collaboration paper page: https://
huggingface.co/papers/2307.05
300
… Human intelligence thrives on the concept of cognitive synergy, where collaboration and information integration among

→ View original post on X — @_akhaliq

12 July 2023

Secrets of RLHF in Large Language Models Part I: PPO

By

@_akhaliq

–

12 July 2023 2h57

Secrets of RLHF in Large Language Models Part I: PPO paper page: https://
huggingface.co/papers/2307.04
964
… Large language models (LLMs) have formulated a blueprint for the advancement of artificial general intelligence. Its primary objective is to function as a human-centric (helpful, honest,

→ View original post on X — @_akhaliq

12 July 2023

Pika Labs Releases Image-Conditioned Video Generation Feature

By

@_akhaliq

–

12 July 2023 2h47

Pika labs releases image-conditioned video generation, upload an image, and the model will animate the image, prompt is “a girl in the wind”pic.twitter.com/QVrYYJjxF6
— AK (@_akhaliq) 12 juillet 2023

Pika labs releases image-conditioned video generation, upload an image, and the model will animate the image, prompt is “a girl in the wind”

→ View original post on X — @_akhaliq

12 July 2023

One-2-3-45: Convert Any Single Image to 3D Mesh in 45 Seconds

By

@_akhaliq

–

12 July 2023 0h54

One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization @Gradio demo is out

demo: https://t.co/IlfEzhOYPV pic.twitter.com/KgbbfnwRi1
— AK (@_akhaliq) 11 juillet 2023

One-2-3-45: Any Single Image to 3D Mesh in 45 Seconds without Per-Shape Optimization @Gradio demo is out demo: https://
huggingface.co/spaces/One-2-3
-45/One-2-3-45
…

→ View original post on X — @_akhaliq

12 July 2023

Reenactment Network with ReshotAI Key Points

By

@_akhaliq

–

11 July 2023 23h22

Reenactment network with reshotAI key points by @alexcarliera
pic.twitter.com/UtRfnrP2w9
— AK (@_akhaliq) 11 juillet 2023

Reenactment network with reshotAI key points by @alexcarliera

→ View original post on X — @_akhaliq

11 July 2023

Objaverse-XL: Massive 10M+ 3D Objects Dataset Released

By

@_akhaliq

–

11 July 2023 22h56

Objaverse-XL: A Universe of 10M+ 3D Objects

paper: https://t.co/Q1iVTAg29Q

Natural language processing and 2D vision models have attained remarkable proficiency on many tasks primarily by escalating the scale of training data. However, 3D vision tasks have not seen the same… pic.twitter.com/ptBAwG9bNF
— AK (@_akhaliq) 11 juillet 2023

Objaverse-XL: A Universe of 10M+ 3D Objects paper: https://
objaverse.allenai.org/objaverse-xl-p
aper.pdf
… Natural language processing and 2D vision models have attained remarkable proficiency on many tasks primarily by escalating the scale of training data. However, 3D vision tasks have not seen the same

→ View original post on X — @_akhaliq

11 July 2023